{"provider_name":"Hatena Blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2020%2F06%2F24%2F224322\" title=\"RNN (3) - \u3089\u3093\u3060\u3080\u306a\u8a18\u61b6\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","published":"2020-06-24 22:43:22","height":"190","url":"https://randommemory.hatenablog.com/entry/2020/06/24/224322","blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","type":"rich","width":"100%","provider_url":"https://hatena.blog","version":"1.0","blog_url":"https://randommemory.hatenablog.com/","author_url":"https://blog.hatena.ne.jp/derwind/","categories":["machine_learning"],"title":"RNN (3)","image_url":null,"author_name":"derwind","description":"\u4f55\u56de\u3081\u306b\u306a\u308b\u304b\u5206\u304b\u3089\u306a\u3044\u3051\u3069\u3001RNN \u306b\u307e\u305f\u30c1\u30e3\u30ec\u30f3\u30b8\u3002https://github.com/oreilly-japan/deep-learning-from-scratch-3/blob/master/steps/step59.py\u306b\u3088\u308b\u6b63\u5f26\u6ce2\u306e\u4e88\u6e2c\u3092\u771f\u4f3c\u308b\u3002 class SimpleRNN(nn.Module): def __init__(self, hidden_size, out_size): super(SimpleRNN, self).__init__() self.rnn = nn.RNN(out_size, hidden_size, nonlinearity=\"tanh\") s\u2026"}